{"id":13423437,"url":"https://github.com/symisc/sod","last_synced_at":"2025-04-08T01:37:11.421Z","repository":{"id":39042647,"uuid":"129008037","full_name":"symisc/sod","owner":"symisc","description":"An Embedded Computer Vision \u0026 Machine Learning Library (CPU Optimized \u0026 IoT Capable)","archived":false,"fork":false,"pushed_at":"2023-10-20T18:32:09.000Z","size":3582,"stargazers_count":1770,"open_issues_count":7,"forks_count":211,"subscribers_count":88,"default_branch":"master","last_synced_at":"2025-04-01T00:34:25.362Z","etag":null,"topics":["c","computer-vision","convolutional-neural-networks","cpu","deep-learning","detection","embedded","face-detection","facial-landmarks","image-analysis","image-processing","image-recognition","iot","iot-device","library","machine-learning-algorithms","object-detection","real-time","vision-framework","webassembly"],"latest_commit_sha":null,"homepage":"https://sod.pixlab.io","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/symisc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-04-10T23:51:01.000Z","updated_at":"2025-03-30T16:14:44.000Z","dependencies_parsed_at":"2022-08-14T10:30:31.109Z","dependency_job_id":"58ea612f-83a4-4b75-b46b-584b3ef33bbf","html_url":"https://github.com/symisc/sod","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/symisc%2Fsod","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/symisc%2Fsod/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/symisc%2Fsod/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/symisc%2Fsod/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/symisc","download_url":"https://codeload.github.com/symisc/sod/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247761050,"owners_count":20991531,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["c","computer-vision","convolutional-neural-networks","cpu","deep-learning","detection","embedded","face-detection","facial-landmarks","image-analysis","image-processing","image-recognition","iot","iot-device","library","machine-learning-algorithms","object-detection","real-time","vision-framework","webassembly"],"created_at":"2024-07-31T00:00:34.550Z","updated_at":"2025-04-08T01:37:11.390Z","avatar_url":"https://github.com/symisc.png","language":"C","readme":"\u003ch1 align=\"center\"\u003eSOD\u003cbr/\u003e\u003cbr/\u003eAn Embedded Computer Vision \u0026 Machine Learning Library\u003cbr/\u003e\u003ca href=\"https://sod.pixlab.io\"\u003esod.pixlab.io\u003c/a\u003e\u003c/h1\u003e\n\n[![API documentation](https://img.shields.io/badge/API%20documentation-Ready-green.svg)](https://sod.pixlab.io/api.html)\n[![dependency](https://img.shields.io/badge/dependency-none-ff96b4.svg)](https://pixlab.io/downloads)\n[![Getting Started](https://img.shields.io/badge/Getting%20Started-Now-f49242.svg)](https://sod.pixlab.io/intro.html)\n[![license](https://img.shields.io/badge/License-dual--licensed-blue.svg)](https://pixlab.io/downloads)\n[![Forum](https://img.shields.io/gitter/room/nwjs/nw.js.svg)](https://community.faceio.net/)\n[![Tiny Dreal](https://pixlab.io/images/logo.png)](https://pixlab.io/tiny-dream)\n\n![Output](https://i.imgur.com/YIbb8wr.jpg)\n\n* [Introduction](#sod-embedded).\n* [Features](#notable-sod-features).\n* [Programming with SOD](#programming-interfaces).\n* [Useful Links](#other-useful-links).\n\n## SOD Embedded\n\n### Release 1.1.9 (July 2023) | [Changelog](https://sod.pixlab.io/changelog.html) |  [Downloads](https://pixlab.io/downloads)\n\nSOD is an embedded, modern cross-platform computer vision and machine learning software library that exposes a set of APIs for deep-learning, advanced media analysis \u0026 processing including real-time, multi-class object detection and model training on embedded systems with limited computational resource and IoT devices.\n\nSOD was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in open source as well commercial products.\n\nDesigned for computational efficiency and with a strong focus on real-time applications. SOD includes a comprehensive set of both classic and state-of-the-art deep-neural networks with their \u003ca href=\"https://pixlab.io/downloads\"\u003epre-trained models\u003c/a\u003e. Built with SOD:\n* \u003ca href=\"https://sod.pixlab.io/intro.html#cnn\"\u003eConvolutional Neural Networks (CNN)\u003c/a\u003e for multi-class (20 and 80) object detection \u0026 classification.\n* \u003ca href=\"https://sod.pixlab.io/api.html#cnn\"\u003eRecurrent Neural Networks (RNN)\u003c/a\u003e for text generation (i.e. Shakespeare, 4chan, Kant, Python code, etc.).\n* \u003ca href=\"https://sod.pixlab.io/samples.html\"\u003eDecision trees\u003c/a\u003e for single class, real-time object detection.\n* A brand new architecture written specifically for SOD named \u003ca href=\"https://sod.pixlab.io/intro.html#realnets\"\u003eRealNets\u003c/a\u003e.\n\n![Multi-class object detection](https://i.imgur.com/Mq98uTv.png) \n\nCross platform, dependency free, amalgamated (single C file) and heavily optimized. Real world use cases includes:\n* Detect \u0026 recognize objects (faces included) at Real-time.\n* License plate extraction.\n* Intrusion detection.\n* Mimic Snapchat filters.\n* Classify human actions.\n* Object identification.\n* Eye \u0026 Pupil tracking.\n* Facial \u0026 Body shape extraction.\n* Image/Frame segmentation.\n\n## Notable SOD features\n\n* Built for real world and real-time applications.\n* State-of-the-art, CPU optimized deep-neural networks including the brand new, exclusive \u003ca href=\"https://sod.pixlab.io/intro.html#realnets\"\u003eRealNets architecture\u003c/a\u003e.\n* Patent-free, advanced computer vision \u003ca href=\"https://sod.pixlab.io/samples.html\"\u003ealgorithms\u003c/a\u003e.\n* Support major \u003ca href=\"https://sod.pixlab.io/api.html#imgproc\"\u003eimage format\u003c/a\u003e.\n* Simple, clean and easy to use \u003ca href=\"https://sod.pixlab.io/api.html\"\u003eAPI\u003c/a\u003e.\n* Brings deep learning on limited computational resource, embedded systems and IoT devices.\n* Easy interpolatable with \u003ca href=\"https://sod.pixlab.io/api.html#cvinter\"\u003eOpenCV\u003c/a\u003e or any other proprietary API.\n* \u003ca href=\"https://pixlab.io/downloads\"\u003ePre-trained models\u003c/a\u003e available for most architectures.\u003c/li\u003e\n* CPU capable, \u003ca href=\"https://sod.pixlab.io/c_api/sod_realnet_train_start.html\"\u003eRealNets model training\u003c/a\u003e.\n* Production ready, cross-platform, high quality source code.\n* SOD is dependency free, written in C, compile and run unmodified on virtually any platform \u0026amp; architecture with a decent C compiler.\n* \u003ca href=\"https://pixlab.io/downloads\"\u003eAmalgamated\u003c/a\u003e - All SOD source files are combined into a single C file (*sod.c*) for easy deployment.\n* Open-source, actively developed \u0026 maintained product.\n* Developer friendly \u003ca href=\"https://sod.pixlab.io/support.html\"\u003esupport channels.\u003c/a\u003e\n\n## Programming Interfaces\n\nThe documentation works both as an API reference and a programming tutorial. It describes the internal structure of the library and guides one in creating applications with a few lines of code. Note that SOD is straightforward to learn, even for new programmer.\n\n Resources |  Description\n------------ | -------------\n\u003ca href=\"https://sod.pixlab.io/intro.html\"\u003eSOD in 5 minutes or less\u003c/a\u003e | A quick introduction to programming with the SOD Embedded C/C++ API with real-world code samples implemented in C.\n\u003ca href=\"https://sod.pixlab.io/api.html\"\u003eC/C++ API Reference Guide\u003c/a\u003e | This document describes each API function in details. This is the reference document you should rely on.\n\u003ca href=\"https://sod.pixlab.io/samples.html\"\u003eC/C++ Code Samples\u003c/a\u003e | Real world code samples on how to embed, load models and start experimenting with SOD.\n\u003ca href=\"https://sod.pixlab.io/articles/license-plate-detection.html\"\u003eLicense Plate Detection\u003c/a\u003e | Learn how to detect vehicles license plates without heavy Machine Learning techniques, just standard image processing routines already implemented in SOD.\n\u003ca href=\"https://sod.pixlab.io/articles/porting-c-face-detector-webassembly.html\"\u003ePorting our Face Detector to WebAssembly\u003c/a\u003e | Learn how we ported the \u003ca href=\"https://sod.pixlab.io/c_api/sod_realnet_detect.html\"\u003eSOD Realnets face detector\u003c/a\u003e into WebAssembly to achieve Real-time performance in the browser.\n\n## Other useful links\n\n Resources |  Description\n------------ | -------------\n\u003ca href=\"https://pixlab.io/downloads\"\u003eDownloads\u003c/a\u003e | Get a copy of the last public release of SOD, pre-trained models, extensions and more. Start embedding and enjoy programming with.\n\u003ca href=\"https://pixlab.io/sod\"\u003eCopyright/Licensing\u003c/a\u003e | SOD is an open-source, dual-licensed product. Find out more about the licensing situation there.\n\u003ca href=\"https://sod.pixlab.io/support.html\"\u003eOnline Support Channels\u003c/a\u003e | Having some trouble integrating SOD? Take a look at our numerous support channels.\n\n![face detection using RealNets](https://i.imgur.com/ZLno8Lz.jpg)\n","funding_links":[],"categories":["C","Algorithm","Data processing"],"sub_categories":["machine learning","CV"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsymisc%2Fsod","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsymisc%2Fsod","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsymisc%2Fsod/lists"}